chainer.Chain

class chainer.Chain(**links)[source]

Composable link with object-like interface.

Composability is one of the most important features of neural nets. Neural net models consist of many reusable fragments, and each model itself might be embedded into a larger learnable system. Chain enables us to write a neural net based on composition, without bothering about routine works like collecting parameters, serialization, copying the structure with parameters shared, etc.

This class actually provides a way to compose one or more links into one structure. A chain can contain one or more child links. Child link is a link registered to the chain with its own name. The child link is stored to an attribute of the chain with the name. User can write a whole model or a fragment of neural nets as a child class of Chain.

Each chain itself is also a link. Therefore, one can combine chains into higher-level chains. In this way, links and chains construct a link hierarchy. Link hierarchy forms a tree structure, where each node is identified by the path from the root. The path is represented by a string like a file path in UNIX, consisting of names of nodes on the path, joined by slashes /.

A child link can be added just by assigning it to an attribute of the chain within init_scope().

The registered child link is saved and loaded on serialization and deserialization, and involved in the optimization. The registered link is called a child. The child link is accessible via children() generator, which returns a generator running through the children in lexical order.

On registration of a child link, its name attribute is also set (or overwritten if the link has already been registered to another chain).

Example

This is a simple example of custom chain definition. Chainer itself also provides some chains defined under the links module. They might serve as examples, too.

Consider we want to define a multi-layer perceptron consisting of two hidden layers with rectifiers as activation functions. We can use the Linear link as a building block:

import chainer
import chainer.functions as F
import chainer.links as L

class MultiLayerPerceptron(chainer.Chain):

    def __init__(self, n_in, n_hidden, n_out):
        super(MultilayerPerceptron, self).__init__()
        with self.init_scope():
            self.layer1 = L.Linear(n_in, n_hidden)
            self.layer2 = L.Linear(n_hidden, n_hidden)
            self.layer3 = L.Linear(n_hidden, n_out)

    def forward(self, x):
        # Forward propagation
        h1 = F.relu(self.layer1(x))
        h2 = F.relu(self.layer2(h1))
        return self.layer3(h2)

Child links are registered via the assignment within a with self.init_scope(): block. The forward propagation is often implemented as the forward operator as the above example, though it is not mandatory.

Parameters:links – Child links. The keywords are used as their names. The names are also set to the links.

Methods

__call__(*args, **kwargs)[source]

Call self as a function.

__getitem__(name)[source]

Equivalent to getattr.

add_hook(hook, name=None)[source]

Registers a link hook.

Parameters:
  • hook (LinkHook) – Link hook to be registered.
  • name (str) – Name of the link hook. The name must be unique among link hooks registered to this link. If None, the default name of the link hook is used.

Registers a child link to this chain.

Parameters:
  • name (str) – Name of the child link. This name is also used as the attribute name.
  • link (Link) – The link object to be registered.
add_param(name, shape=None, dtype=<class 'numpy.float32'>, initializer=None)[source]

Registers a parameter to the link.

Parameters:
  • name (str) – Name of the parameter. This name is also used as the attribute name.
  • shape (int or tuple of ints) – Shape of the parameter array. If it is omitted, the parameter variable is left uninitialized.
  • dtype – Data type of the parameter array.
  • initializer – If it is not None, the data is initialized with the given initializer. If it is an array, the data is directly initialized by it. If it is callable, it is used as a weight initializer. Note that in these cases, dtype argument is ignored.
add_persistent(name, value)[source]

Registers a persistent value to the link.

The registered value is saved and loaded on serialization and deserialization. The value is set to an attribute of the link.

Parameters:
  • name (str) – Name of the persistent value. This name is also used for the attribute name.
  • value – Value to be registered.
addgrads(link)[source]

Accumulates gradient values from given link.

This method adds each gradient array of the given link to corresponding gradient array of this link. The accumulation is even done across host and different devices.

Parameters:link (Link) – Source link object.
children()[source]

Returns a generator of all child links.

Returns:A generator object that generates all child links.
cleargrads()[source]

Clears all gradient arrays.

This method should be called before the backward computation at every iteration of the optimization.

copy(mode='share')[source]

Copies the link hierarchy to new one.

The whole hierarchy rooted by this link is copied. There are three modes to perform copy. Please see the documentation for the argument mode below.

The name of the link is reset on the copy, since the copied instance does not belong to the original parent chain (even if exists).

Parameters:mode (str) – It should be either init, copy, or share. init means parameter variables under the returned link object is re-initialized by calling their initialize() method, so that all the parameters may have different initial values from the original link. copy means that the link object is deeply copied, so that its parameters are not re-initialized but are also deeply copied. Thus, all parameters have same initial values but can be changed independently. share means that the link is shallowly copied, so that its parameters’ arrays are shared with the original one. Thus, their values are changed synchronously. The default mode is share.
Returns:Copied link object.
Return type:Link
copyparams(link, copy_persistent=True)[source]

Copies all parameters from given link.

This method copies data arrays of all parameters in the hierarchy. The copy is even done across the host and devices. Note that this method does not copy the gradient arrays.

From v5.0.0: this method also copies the persistent values (e.g. the moving statistics of BatchNormalization). If the persistent value is an ndarray, the elements are copied. Otherwise, it is copied using copy.deepcopy(). The old behavior (not copying persistent values) can be reproduced with copy_persistent=False.

Parameters:
  • link (Link) – Source link object.
  • copy_persistent (bool) – If True, persistent values are also copied. True by default.
count_params()[source]

Counts the total number of parameters.

This method counts the total number of scalar values included in all the Parameters held by this link and its descendants.

If the link containts uninitialized parameters, this method raises a warning.

Returns:The total size of parameters (int)
delete_hook(name)[source]

Unregisters the link hook.

Parameters:name (str) – The name of the link hook to be unregistered.
disable_update()[source]

Disables update rules of all parameters under the link hierarchy.

This method sets the enabled flag of the update rule of each parameter variable to False.

enable_update()[source]

Enables update rules of all parameters under the link hierarchy.

This method sets the enabled flag of the update rule of each parameter variable to True.

init_scope()[source]

Creates an initialization scope.

This method returns a context manager object that enables registration of parameters (and links for Chain) by an assignment. A Parameter object can be automatically registered by assigning it to an attribute under this context manager.

Example

In most cases, the parameter registration is done in the initializer method. Using the init_scope method, we can simply assign a Parameter object to register it to the link.

class MyLink(chainer.Link):
    def __init__(self):
        super().__init__()
        with self.init_scope():
            self.W = chainer.Parameter(0, (10, 5))
            self.b = chainer.Parameter(0, (5,))

Returns a generator of all links under the hierarchy.

Parameters:skipself (bool) – If True, then the generator skips this link and starts with the first child link.
Returns:A generator object that generates all links.

Returns a generator of all (path, link) pairs under the hierarchy.

Parameters:skipself (bool) – If True, then the generator skips this link and starts with the first child link.
Returns:A generator object that generates all (path, link) pairs.
namedparams(include_uninit=True)[source]

Returns a generator of all (path, param) pairs under the hierarchy.

Parameters:include_uninit (bool) – If True, it also generates uninitialized parameters.
Returns:A generator object that generates all (path, parameter) pairs. The paths are relative from this link.
params(include_uninit=True)[source]

Returns a generator of all parameters under the link hierarchy.

Parameters:include_uninit (bool) – If True, it also generates uninitialized parameters.
Returns:A generator object that generates all parameters.
register_persistent(name)[source]

Registers an attribute of a given name as a persistent value.

This is a convenient method to register an existing attribute as a persistent value. If name has been already registered as a parameter, this method removes it from the list of parameter names and re-registers it as a persistent value.

Parameters:name (str) – Name of the attribute to be registered.
repeat(n_repeat, mode='init')[source]

Repeats this link multiple times to make a Sequential.

This method returns a Sequential object which has the same Link multiple times repeatedly. The mode argument means how to copy this link to repeat.

Example

You can repeat the same link multiple times to create a longer Sequential block like this:

class ConvBNReLU(chainer.Chain):

    def __init__(self):
        super(ConvBNReLU, self).__init__()
        with self.init_scope():
            self.conv = L.Convolution2D(
                None, 64, 3, 1, 1, nobias=True)
            self.bn = L.BatchNormalization(64)

    def forward(self, x):
        return F.relu(self.bn(self.conv(x)))

net = ConvBNReLU().repeat(16, mode='init')

The net object contains 16 blocks, each of which is ConvBNReLU. And the mode was init, so each block is re-initialized with different parameters. If you give copy to this argument, each block has same values for its parameters but its object ID is different from others. If it is share, each block is same to others in terms of not only parameters but also the object IDs because they are shallow-copied, so that when the parameter of one block is changed, all the parameters in the others also change.

Parameters:
  • n_repeat (int) – Number of times to repeat.
  • mode (str) – It should be either init, copy, or share. init means parameters of each repeated element in the returned Sequential will be re-initialized, so that all elements have different initial parameters. copy means that the parameters will not be re-initialized but object itself will be deep-copied, so that all elements have same initial parameters but can be changed independently. share means all the elements which consist the resulting Sequential object are same object because they are shallow-copied, so that all parameters of elements are shared with each other.
serialize(serializer)[source]

Serializes the link object.

Parameters:serializer (AbstractSerializer) – Serializer object.
to_cpu()[source]

Copies parameter variables and persistent values to CPU.

This method does not handle non-registered attributes. If some of such attributes must be copied to CPU, the link implementation must override this method to do so.

Returns: self

to_gpu(device=None)[source]

Copies parameter variables and persistent values to GPU.

This method does not handle non-registered attributes. If some of such attributes must be copied to GPU, the link implementation must override this method to do so.

Parameters:device – Target device specifier. If omitted, the current device is used.

Returns: self

to_intel64()[source]

Copies parameter variables and persistent values to CPU.

zerograds()[source]

Initializes all gradient arrays by zero.

This method can be used for the same purpose of cleargrads, but less efficient. This method is left for backward compatibility.

Deprecated since version v1.15: Use cleargrads() instead.

Attributes

Ordered dictionary of registered link hooks.

Contrary to chainer.thread_local.link_hooks, which registers its elements to all functions, link hooks in this property are specific to this link.

update_enabled

True if at least one parameter has an update rule enabled.

within_init_scope

True if the current code is inside of an initialization scope.

See init_scope() for the details of the initialization scope.

xp

Array module for this link.

Depending on which of CPU/GPU this link is on, this property returns numpy or cupy.